Upsonic provides a Python framework for creating autonomous AI agents.
AgentRun
AgentRun provides a way to execute Python code generated by AI systems.

About AgentRun
AgentRun is an open-source Python library for executing Python code generated by large language models. It checks code for dangerous elements before execution and runs it in an isolated Docker container, with configurable resource limits and timeouts, control over allowed dependencies with optional caching, automatic install and cleanup, and direct return of Python exceptions and tracebacks.
It can be installed via pip for use with an existing running Docker container, or run as a self-hostable REST API using the included Docker Compose setup. The repository notes the REST API path for users not comfortable configuring Docker.
Key features
- Checks generated code for dangerous elements before execution
- Executes code in isolated Docker container
- Supports configurable resource limits and execution timeouts
- Controls allowed dependencies with optional caching
- Returns Python exceptions and tracebacks directly
- Provides self-hostable REST API or pip install option
- Checks code before execution and runs it in an isolated Docker container
- Includes Docker Compose setup with REST API for self-hosting
- Has 97% test coverage with full static typing and two dependencies
- Requires Docker; pip use needs a running container you configure
AgentRun at a glance
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
AgentRun alternatives
Tools and sites you could use instead, ranked by how closely they match.
BondAI is a tool for developing AI agent systems, with memory management, error handling, search, and integrations.
AG2 offers open source tools for building and coordinating AI agent systems.
Agent4Rec implements research on generative agents for recommendation systems.
Opik helps debug, evaluate, and monitor LLM applications, RAG systems, and agent workflows with tracing and evaluations.
An experimental open source project exploring a fully autonomous GPT-4 system.
Popular in AI Agents & Automation
Well-known listings from the same topic.
AgentRun FAQ
What are the ways to use AgentRun?
How does AgentRun handle dependencies?
What execution controls are available?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












